import pandas as pd
import numpy as np
import chart_studio.plotly as py
import cufflinks as cf
import seaborn as sns
import plotly.express as px
%matplotlib inline

# Make Plotly work in your Jupyter Notebook
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import plotly.graph_objs as go

# Use Plotly locally
cf.go_offline()

Simple scatter plot

N=100
x=np.random.rand(N)
y=np.random.rand(N)

trace=go.Scatter(
    x=x,
    y=y,
    mode='markers')

data=[trace]
iplot(data)

working with Iris data set

df_iris = px.data.iris()
df_iris.head()

	sepal_length	sepal_width	petal_length	petal_width	species	species_id
0	5.1	3.5	1.4	0.2	setosa	1
1	4.9	3.0	1.4	0.2	setosa	1
2	4.7	3.2	1.3	0.2	setosa	1
3	4.6	3.1	1.5	0.2	setosa	1
4	5.0	3.6	1.4	0.2	setosa	1

Create a scatter plot by defining x, y, different color for count of provided column, size based on supplied column and additional data to display on hover

px.scatter(df_iris, x="sepal_width", y="sepal_length", color="species",
                 size='petal_length', hover_data=['petal_width'])

Create a customized scatter with black marker edges with line width 2, opaque and colored based on width. Also show a scale on the right

fig = go.Figure()
fig.add_trace(go.Scatter(
    x=df_iris.sepal_width, y=df_iris.sepal_length,
    mode='markers',
    marker_color=df_iris.sepal_width,
    text=df_iris.species,
    marker=dict(showscale=True)
))
fig.update_traces(marker_line_width=2, marker_size=10)

# Working with a lot of data use Scattergl

fig = go.Figure(data=go.Scattergl(
    x = np.random.randn(100000),
    y = np.random.randn(100000),
    mode='markers',
    marker=dict(
        color=np.random.randn(100000),
        colorscale='Viridis',
        line_width=1
    )
))
fig

Scatter Matrix

• With a scatter matrix we can compare changes when comparing column data

flights = sns.load_dataset("flights")
flights.head()

	year	month	passengers
0	1949	Jan	112
1	1949	Feb	118
2	1949	Mar	132
3	1949	Apr	129
4	1949	May	121

fig = px.scatter_matrix(flights, color='month')
fig

Pie Charts

#Expenses
groups=['Rent', 'Food', 'Bills', 'Miscellenous']
amount=[1000,530,678,970]
colors=['#d32c58','#f9blee','#b7f9b1','#bif5f9']
trace=go.Pie(labels=groups, values=amount,
            hoverinfo='label+percent', textinfo='value',
            textfont=dict(size=20),
            marker=dict(colors=colors,
                        line=dict(color='#000000', width=4)))
iplot([trace])

Create Pie chart of the largest nations in Asia

df= px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

df_asia = df.query("year == 2007").query("continent == 'Asia'")
df_asia.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
11	Afghanistan	Asia	2007	43.828	31889923	974.580338	AFG	4
95	Bahrain	Asia	2007	75.635	708573	29796.048340	BHR	48
107	Bangladesh	Asia	2007	64.062	150448339	1391.253792	BGD	50
227	Cambodia	Asia	2007	59.723	14131858	1713.778686	KHM	116
299	China	Asia	2007	72.961	1318683096	4959.114854	CHN	156

px.pie(df_asia, values='pop', names='country', 
       title='Population of Asian continent', 
       color_discrete_sequence=px.colors.sequential.RdBu)

Customize pie chart

colors = ['blue', 'green', 'black', 'purple', 'red', 'brown']
fig = go.Figure(data=[go.Pie(labels=['Water','Grass','Normal','Psychic', 'Fire', 'Ground'], 
                       values=[110,90,80,80,70,60])])

# Define hover info, text size, pull amount for each pie slice, and stroke
fig.update_traces(hoverinfo='label+percent', textfont_size=15,
                  textinfo='label+percent', pull=[0.1, 0, 0.2, 0, 0, 0],
                  marker=dict(colors=colors, line=dict(color='#FFFFFF', width=2)))